[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M797EDPB6512THSZ0RMS4PSY":3,"skill-same:01M797EDPB6512THSZ0RMS4PSY":79},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":33,"install":34,"resources":46},"01M797EDPB6512THSZ0RMS4PSY","worldgen",null,"Guides WorldGen workflows for generating 3D scenes from text, images, panoramas, or the interactive demo, including Gaussian-splat and mesh outputs.","VectorSpaceLab\u002FAREX-Skill","VectorSpaceLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180637102?v=4","01M7538C5WPSJGWF7KHR4EFZ9F","01M7538C6R2GFP53NPXTCZNBRT",351,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fworldgen\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: worldgen\ndescription: \"Guides WorldGen workflows for generating 3D scenes from text,\n  images, panoramas, or the interactive demo, including Gaussian-splat and mesh\n  outputs.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# WorldGen\n\nWorldGen turns text prompts, source images, or equirectangular panoramas into\n3D scenes. The main pipeline generates a 360 panorama, predicts depth, and\nconverts the result into a Gaussian splat or an Open3D mesh; the bundled viewer\nadds browser-based free-view exploration and novel-view export.\n\n## Install and import check\n\nWorldGen targets Python 3.11 and a CUDA-capable PyTorch environment for real\nscene generation:\n\n```bash\npython -m pip install -e .\npython scripts\u002Fcheck_worldgen_env.py --demo-help\n```\n\nThe package also needs the external DA-2\u002FPyTorch3D\u002FNunchaku\u002FOpen3D\u002FViser stack\nshown in [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md). Keep\nthose compiled dependencies on a compatible Python, torch, and CUDA ABI.\n\n## Route by task\n\n- **Generate from text, an image, or a panorama; select splat or mesh output**:\n  use [`sub-skills\u002Fscene-generation\u002FSKILL.md`](sub-skills\u002Fscene-generation\u002FSKILL.md).\n- **Run the interactive browser viewer or save novel views**: use the same\n  scene-generation route and [`references\u002Fcli-reference.md`](references\u002Fcli-reference.md).\n- **Inspect constructor, method, tensor, and output contracts**: read\n  [`references\u002Fapi-reference.md`](references\u002Fapi-reference.md).\n- **Diagnose installation, CUDA, model downloads, optional Sharp\u002Finpainting, or\n  viewer failures**: read [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md)\n  and then the scene-generation troubleshooting reference.\n- **Check freshness against the source checkout**: read\n  [`references\u002Frepo-provenance.md`](references\u002Frepo-provenance.md).\n\n## Common starting points\n\n- Begin with the scene-generation sub-skill for `WorldGen(mode=\"t2s\")`,\n  `WorldGen(mode=\"i2s\")`, `_generate_world(pano_image)`, or `return_mesh=True`.\n- Use `scripts\u002Fcheck_worldgen_env.py` before any long model download. It checks\n  imports, public signatures, and a tiny CUDA allocation without loading weights.\n- Use `scripts\u002Fworldgen_demo.py --help` to inspect the self-contained interactive\n  launcher. It does not depend on the original repository checkout.\n- Treat `use_sharp=True` and `inpaint_bg=True` as optional experimental branches;\n  validate the default splat or mesh path first.\n\n## Shared references and scripts\n\n- [`references\u002Fapi-reference.md`](references\u002Fapi-reference.md) contains verified\n  signatures, mode rules, output types, and lower-level conversion helpers.\n- [`references\u002Fcli-reference.md`](references\u002Fcli-reference.md) documents the\n  bundled demo flags, output files, viewer behavior, and safe preflight.\n- [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) covers\n  install\u002Fimport, CUDA, VRAM, model access, input validation, and viewer errors.\n- [`scripts\u002Fcheck_worldgen_env.py`](scripts\u002Fcheck_worldgen_env.py) runs the\n  read-only import\u002FAPI\u002FCUDA smoke check.\n- [`scripts\u002Fworldgen_demo.py`](scripts\u002Fworldgen_demo.py) is the bundled,\n  self-contained Viser launcher adapted from the repo's public demo workflow.\n\n## Boundaries\n\nThis is a runtime user skill for WorldGen's generation and visualization\nsurface. It does not cover model training, release engineering, repository\nmaintenance, upstream DA-2\u002FPyTorch3D development, or generic Open3D\u002FViser usage\nwithout WorldGen. Optional Sharp and background-inpainting guidance is included\nonly as an explicitly unverified extension to the core generation route.\n","# WorldGen\n\nWorldGen turns text prompts, source images, or equirectangular panoramas into\n3D scenes. The main pipeline generates a 360 panorama, predicts depth, and\nconverts the result into a Gaussian splat or an Open3D mesh; the bundled viewer\nadds browser-based free-view exploration and novel-view export.\n\n## Install and import check\n\nWorldGen targets Python 3.11 and a CUDA-capable PyTorch environment for real\nscene generation:\n\n```bash\npython -m pip install -e .\npython scripts\u002Fcheck_worldgen_env.py --demo-help\n```\n\nThe package also needs the external DA-2\u002FPyTorch3D\u002FNunchaku\u002FOpen3D\u002FViser stack\nshown in [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md). Keep\nthose compiled dependencies on a compatible Python, torch, and CUDA ABI.\n\n## Route by task\n\n- **Generate from text, an image, or a panorama; select splat or mesh output**:\n  use [`sub-skills\u002Fscene-generation\u002FSKILL.md`](sub-skills\u002Fscene-generation\u002FSKILL.md).\n- **Run the interactive browser viewer or save novel views**: use the same\n  scene-generation route and [`references\u002Fcli-reference.md`](references\u002Fcli-reference.md).\n- **Inspect constructor, method, tensor, and output contracts**: read\n  [`references\u002Fapi-reference.md`](references\u002Fapi-reference.md).\n- **Diagnose installation, CUDA, model downloads, optional Sharp\u002Finpainting, or\n  viewer failures**: read [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md)\n  and then the scene-generation troubleshooting reference.\n- **Check freshness against the source checkout**: read\n  [`references\u002Frepo-provenance.md`](references\u002Frepo-provenance.md).\n\n## Common starting points\n\n- Begin with the scene-generation sub-skill for `WorldGen(mode=\"t2s\")`,\n  `WorldGen(mode=\"i2s\")`, `_generate_world(pano_image)`, or `return_mesh=True`.\n- Use `scripts\u002Fcheck_worldgen_env.py` before any long model download. It checks\n  imports, public signatures, and a tiny CUDA allocation without loading weights.\n- Use `scripts\u002Fworldgen_demo.py --help` to inspect the self-contained interactive\n  launcher. It does not depend on the original repository checkout.\n- Treat `use_sharp=True` and `inpaint_bg=True` as optional experimental branches;\n  validate the default splat or mesh path first.\n\n## Shared references and scripts\n\n- [`references\u002Fapi-reference.md`](references\u002Fapi-reference.md) contains verified\n  signatures, mode rules, output types, and lower-level conversion helpers.\n- [`references\u002Fcli-reference.md`](references\u002Fcli-reference.md) documents the\n  bundled demo flags, output files, viewer behavior, and safe preflight.\n- [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) covers\n  install\u002Fimport, CUDA, VRAM, model access, input validation, and viewer errors.\n- [`scripts\u002Fcheck_worldgen_env.py`](scripts\u002Fcheck_worldgen_env.py) runs the\n  read-only import\u002FAPI\u002FCUDA smoke check.\n- [`scripts\u002Fworldgen_demo.py`](scripts\u002Fworldgen_demo.py) is the bundled,\n  self-contained Viser launcher adapted from the repo's public demo workflow.\n\n## Boundaries\n\nThis is a runtime user skill for WorldGen's generation and visualization\nsurface. It does not cover model training, release engineering, repository\nmaintenance, upstream DA-2\u002FPyTorch3D development, or generic Open3D\u002FViser usage\nwithout WorldGen. Optional Sharp and background-inpainting guidance is included\nonly as an explicitly unverified extension to the core generation route.\n",{"name":5,"license":23,"metadata":24,"description":7,"disable-model-invocation":26},"Apache 2.0",{"disco-role":25},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fworldgen",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":26},[36,39,42],{"tool":37,"command":38},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill worldgen",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill worldgen",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill worldgen","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fworldgen\u002FSKILL.md",[47,53,57,61,65,69,75],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fapi-reference.md","REFERENCE","参考文档",5700,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fworldgen\u002Freferences\u002Fapi-reference.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fcli-reference.md",3020,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fworldgen\u002Freferences\u002Fcli-reference.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Frepo-provenance.md",1263,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fworldgen\u002Freferences\u002Frepo-provenance.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Frepo-routing-metadata.json",405,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fworldgen\u002Freferences\u002Frepo-routing-metadata.json",{"path":66,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":67,"sourceHtmlUrl":68},"references\u002Ftroubleshooting.md",6196,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fworldgen\u002Freferences\u002Ftroubleshooting.md",{"path":70,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":73,"sourceHtmlUrl":74},"scripts\u002Fcheck_worldgen_env.py","SCRIPT","脚本",1943,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fworldgen\u002Fscripts\u002Fcheck_worldgen_env.py",{"path":76,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":77,"sourceHtmlUrl":78},"scripts\u002Fworldgen_demo.py",13186,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fworldgen\u002Fscripts\u002Fworldgen_demo.py",[80,87,94,101,108,115],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":18},"01M799NYSH1R3RVAHSM2D88Y84","passnet-triton-opt","Make a single PassNet Triton kernel fast AND numerically faithful: performance model (when a replacement can win at all), block\u002Fgrid\u002Fwarp tuning, autotune policy, launch overhead, and per-op numeric recipes to pass the dtype baseline tolerances. Use when a pass matches and is correct but speedup below expected, or when correctness fails by small numeric margins.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-triton-opt\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":18},"01M799NS5APEC0N1FZ7XZVW6BN","passnet-solve","END-TO-END playbook for solving one PassNet sample: analyze the computation graphs, decide the optimization strategy (what to fuse, what to replace, what to leave alone), drive the iteration loop, and maximize the sample score. This is the ENTRY skill — invoke it first for any PassNet optimization task; it tells you when to use passnet-pattern-fusion, passnet-triton-opt and passnet-feedback.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-solve\u002FSKILL.md",[],[],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":18},"01M799NNY9BKSM21V5R7QVTBJX","passnet-skill","PassNet GPU kernel optimization via compiler passes. Design and implement Triton-based optimization passes, create pass files under .\u002Fpass_dir\u002F, self-evaluate with pass_evaluator, and iterate to maximize GPU speedup.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-skill\u002FSKILL.md",[],[],{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":18},"01M799NHH6NP7Z1RK77KGXAN6S","passnet-pattern-fusion","Author PassNet pass files: write patterns that actually MATCH the FX graph, pick fusion regions (which ops to absorb into one Triton kernel), and structure multi-pass submissions with the mandatory shared-dispatch architecture. Use when creating or fixing pattern()\u002Freplacement_args()\u002Freplacement_func() files, when a pass \"failed to match\", or when deciding how to fuse multiple kernels\u002Fops.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-pattern-fusion\u002FSKILL.md",[],[],{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":114,"publishedAt":18},"01M799ND2J4WNC2PGAZ0A06NDF","passnet-orchestrate","Round\u002Fbatch planning and decision support for PassNet graph optimization. Use for multi-sample triage, worker allocation, eval-budget policy, and post-eval keep\u002Frevert decisions. For solving one concrete sample end to end, use passnet-solve as the entry skill; consult this skill only when you need broader planning or a specific decision gate.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-orchestrate\u002FSKILL.md",[],[],{"skillNo":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":121,"publishedAt":18},"01M799N8SBTMY02ZDG2AZF5ZWE","passnet-feedback","Fast, deterministic feedback for PassNet work: pre-flight pattern\u002Fmatch verification WITHOUT burning a GPU evaluation, per-node bottleneck analysis of a sample's graphs, and eval-log parsing into per-variant status + estimated score + failure classification. Use BEFORE every GPU evaluation (check_pattern), at the START of a sample (analyze_graph), and AFTER every evaluation (parse_eval_log).","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-feedback\u002FSKILL.md",[],[]]